oddskool

import numpy as np
from sklearn.linear import LogisticRegression
from sklearn.metrics import hamming_loss

def c2st(X, y, clf=LogisticRegression(), loss=hamming_loss, bootstraps=300):
    """
    Perform Classifier Two Sample Test (C2ST) [1].
    
    This test estimates if a target is predictable from features by comparing the loss of a classifier learning 
    the true target with the distribution of losses of classifiers learning a random target with the same average.

oddskool

import array
import csv
import numpy as np
from scipy.sparse import csr_matrix

def csv_to_csr(f):
    """Read content of CSV file f, return as CSR matrix."""
    data = array.array("f")
    indices = array.array("i")
    indptr = array.array("i", [0])

oddskool

oddskool

oddskool

{
 "metadata": {
  "language": "Julia",
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

oddskool

from scipy.sparse.csr import csr_matrix
import sys
import numpy as np
from scipy.sparse.base import issparse
from sklearn.linear_model.stochastic_gradient import SGDRegressor
from sklearn.metrics import r2_score

np.random.seed(42)

n_samples, n_features = 300, 30

oddskool

import sys
import boto
from collections import defaultdict

s3 = boto.connect_s3()
bucket = s3.lookup(sys.argv[1])

total_bytes = defaultdict(int)

def process(key):

oddskool

# -*- coding:utf-8 -*-
'''
Simplistic script to parse the detailed AWS billing CSV file.

Script displays cost of S3 operations broken down per region, bucket and usage 
type (either storage or network). It also sums up the amount of storage used per bucket. 
Output is filtered wrt to costs < 1$.

See http://docs.aws.amazon.com/awsaccountbilling/latest/about/programaccess.html for 
how to set up programmatic access to your billing.

oddskool

from collections import defaultdict
import re
import numpy as np

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction import FeatureHasher
from sklearn.linear_model.stochastic_gradient import SGDClassifier
from sklearn.externals import joblib

def tokens(doc):

oddskool

import random

class EpsilonGreedyBandit(Bandit):
    """
    The best action (as much as the algorithm knows so far) is selected for
    a proportion 1 - \epsilon of the trials, and another action is randomly
    selected (with uniform probability) for a proportion \epsilon.

    Parameters
    ----------